| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193 |
- architecture: YOLOv3
- use_gpu: true
- max_iters: 300000
- log_smooth_window: 100
- log_iter: 100
- save_dir: output
- snapshot_iter: 10000
- metric: COCO
- pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_5_pretrained.tar
- weights: output/ppyolo_tiny/model_final
- num_classes: 80
- use_fine_grained_loss: true
- use_ema: true
- ema_decay: 0.9998
- YOLOv3:
- backbone: MobileNetV3
- yolo_head: PPYOLOTinyHead
- use_fine_grained_loss: true
- MobileNetV3:
- norm_type: sync_bn
- norm_decay: 0.
- model_name: large
- scale: .5
- extra_block_filters: []
- feature_maps: [1, 2, 3, 4, 6]
- PPYOLOTinyHead:
- anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
- anchors: [[10, 15], [24, 36], [72, 42],
- [35, 87], [102, 96], [60, 170],
- [220, 125], [128, 222], [264, 266]]
- detection_block_channels: [160, 128, 96]
- norm_decay: 0.
- scale_x_y: 1.05
- yolo_loss: YOLOv3Loss
- spp: true
- drop_block: true
- nms:
- background_label: -1
- keep_top_k: 100
- nms_threshold: 0.45
- nms_top_k: 1000
- normalized: false
- score_threshold: 0.01
- YOLOv3Loss:
- ignore_thresh: 0.5
- scale_x_y: 1.05
- label_smooth: false
- use_fine_grained_loss: true
- iou_loss: IouLoss
- IouLoss:
- loss_weight: 2.5
- max_height: 512
- max_width: 512
- LearningRate:
- base_lr: 0.005
- schedulers:
- - !PiecewiseDecay
- gamma: 0.1
- milestones:
- - 200000
- - 250000
- - 280000
- - !LinearWarmup
- start_factor: 0.
- steps: 4000
- OptimizerBuilder:
- optimizer:
- momentum: 0.949
- type: Momentum
- regularizer:
- factor: 0.0005
- type: L2
- TrainReader:
- inputs_def:
- fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
- num_max_boxes: 100
- dataset:
- !COCODataSet
- image_dir: train2017
- anno_path: annotations/instances_train2017.json
- dataset_dir: train_data/dataset/coco
- with_background: false
- sample_transforms:
- - !DecodeImage
- to_rgb: True
- with_mixup: True
- - !MixupImage
- alpha: 1.5
- beta: 1.5
- - !ColorDistort {}
- - !RandomExpand
- fill_value: [123.675, 116.28, 103.53]
- ratio: 2
- - !RandomCrop {}
- - !RandomFlipImage
- is_normalized: false
- - !NormalizeBox {}
- - !PadBox
- num_max_boxes: 100
- - !BboxXYXY2XYWH {}
- batch_transforms:
- - !RandomShape
- sizes: [192, 224, 256, 288, 320, 352, 384, 416, 448, 480, 512]
- random_inter: True
- - !NormalizeImage
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- is_scale: True
- is_channel_first: false
- - !Permute
- to_bgr: false
- channel_first: True
- # Gt2YoloTarget is only used when use_fine_grained_loss set as true,
- # this operator will be deleted automatically if use_fine_grained_loss
- # is set as false
- - !Gt2YoloTarget
- anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
- anchors: [[10, 15], [24, 36], [72, 42],
- [35, 87], [102, 96], [60, 170],
- [220, 125], [128, 222], [264, 266]]
- downsample_ratios: [32, 16, 8]
- iou_thresh: 0.25
- num_classes: 80
- batch_size: 32
- shuffle: true
- mixup_epoch: 200
- drop_last: true
- worker_num: 16
- bufsize: 4
- use_process: true
- EvalReader:
- inputs_def:
- fields: ['image', 'im_size', 'im_id']
- num_max_boxes: 100
- dataset:
- !COCODataSet
- image_dir: val2017
- anno_path: annotations/instances_val2017.json
- dataset_dir: train_data/dataset/coco
- with_background: false
- sample_transforms:
- - !DecodeImage
- to_rgb: True
- - !ResizeImage
- target_size: 320
- interp: 2
- - !NormalizeImage
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- is_scale: True
- is_channel_first: false
- - !PadBox
- num_max_boxes: 100
- - !Permute
- to_bgr: false
- channel_first: True
- batch_size: 1
- drop_empty: false
- worker_num: 2
- bufsize: 4
- TestReader:
- inputs_def:
- image_shape: [3, 320, 320]
- fields: ['image', 'im_size', 'im_id']
- dataset:
- !ImageFolder
- anno_path: annotations/instances_val2017.json
- with_background: false
- sample_transforms:
- - !DecodeImage
- to_rgb: True
- - !ResizeImage
- target_size: 320
- interp: 2
- - !NormalizeImage
- mean: [0.485, 0.456, 0.406]
- std: [0.229, 0.224, 0.225]
- is_scale: True
- is_channel_first: false
- - !Permute
- to_bgr: false
- channel_first: True
- batch_size: 1
|
